@inproceedings{chen-etal-2019-recurrent,
title = "Recurrent Positional Embedding for Neural Machine Translation",
author = "Chen, Kehai and
Wang, Rui and
Utiyama, Masao and
Sumita, Eiichiro",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1139",
doi = "10.18653/v1/D19-1139",
pages = "1361--1367",
abstract = "In the Transformer network architecture, positional embeddings are used to encode order dependencies into the input representation. However, this input representation only involves static order dependencies based on discrete numerical information, that is, are independent of word content. To address this issue, this work proposes a recurrent positional embedding approach based on word vector. In this approach, these recurrent positional embeddings are learned by a recurrent neural network, encoding word content-based order dependencies into the input representation. They are then integrated into the existing multi-head self-attention model as independent heads or part of each head. The experimental results revealed that the proposed approach improved translation performance over that of the state-of-the-art Transformer baseline in WMT{'}14 English-to-German and NIST Chinese-to-English translation tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2019-recurrent">
<titleInfo>
<title>Recurrent Positional Embedding for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kehai</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the Transformer network architecture, positional embeddings are used to encode order dependencies into the input representation. However, this input representation only involves static order dependencies based on discrete numerical information, that is, are independent of word content. To address this issue, this work proposes a recurrent positional embedding approach based on word vector. In this approach, these recurrent positional embeddings are learned by a recurrent neural network, encoding word content-based order dependencies into the input representation. They are then integrated into the existing multi-head self-attention model as independent heads or part of each head. The experimental results revealed that the proposed approach improved translation performance over that of the state-of-the-art Transformer baseline in WMT’14 English-to-German and NIST Chinese-to-English translation tasks.</abstract>
<identifier type="citekey">chen-etal-2019-recurrent</identifier>
<identifier type="doi">10.18653/v1/D19-1139</identifier>
<location>
<url>https://aclanthology.org/D19-1139</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>1361</start>
<end>1367</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recurrent Positional Embedding for Neural Machine Translation
%A Chen, Kehai
%A Wang, Rui
%A Utiyama, Masao
%A Sumita, Eiichiro
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F chen-etal-2019-recurrent
%X In the Transformer network architecture, positional embeddings are used to encode order dependencies into the input representation. However, this input representation only involves static order dependencies based on discrete numerical information, that is, are independent of word content. To address this issue, this work proposes a recurrent positional embedding approach based on word vector. In this approach, these recurrent positional embeddings are learned by a recurrent neural network, encoding word content-based order dependencies into the input representation. They are then integrated into the existing multi-head self-attention model as independent heads or part of each head. The experimental results revealed that the proposed approach improved translation performance over that of the state-of-the-art Transformer baseline in WMT’14 English-to-German and NIST Chinese-to-English translation tasks.
%R 10.18653/v1/D19-1139
%U https://aclanthology.org/D19-1139
%U https://doi.org/10.18653/v1/D19-1139
%P 1361-1367
Markdown (Informal)
[Recurrent Positional Embedding for Neural Machine Translation](https://aclanthology.org/D19-1139) (Chen et al., EMNLP-IJCNLP 2019)
ACL
- Kehai Chen, Rui Wang, Masao Utiyama, and Eiichiro Sumita. 2019. Recurrent Positional Embedding for Neural Machine Translation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1361–1367, Hong Kong, China. Association for Computational Linguistics.